MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?
Official Schedule Context
- Date/time: 2026-06-30 · 3:20pm-3:40pm
- Track/room: Context Engineering · Track 8
- Speaker(s): Cornelia Davis
- Session type/status: session · confirmed
Official Description
The November 2025 MCP spec release introduced tasks, a way to make tool calls in an async manner.
But more than 5 months later (an eternity in AI-time) there are still NO clients that support it -
not Claude, not Codex, not even goose! I believe there are two reasons: Designing the client
experience when there are potentially 1000s of background tasks running on their own schedule and
engaging humans at unpredictable times is a challenge. And tasks place new infrastructure
requirements on such a client. This talk will share the findings from having built against the tasks
protocol and will suggest solutions these problems. Yup, we'll have a working client!
Related YouTube Video
OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.
Supporting Slides
- youtube k8cnVCMYmNc slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube k8cnVCMYmNc dense slides (11 viable slide images).
- Related slide/OCR pages:
- youtube k8cnVCMYmNc dense slides
- youtube k8cnVCMYmNc reconstructed slides
- youtube k8cnVCMYmNc slides
- Slide-derived terms:
temporal,completed,python,tools,alerts,pycache,here,result,weather,openal,instructions,today,york,skies,clear,start_workflow,model,support